coder

An implementation agent that writes production code using TDD, a method of writing tests before the code they check, and commits the completed changes.

In plain words
What is it for?
Use it to implement features, fix bugs, and write code after a plan is approved. It hands completed work to quality assurance.
Why use it?
It ensures work follows a confirmed plan and sends unclear requirements back for planning instead of guessing.

Agent for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/snyk/snyk-ls/coder
Clone the repo
git clone --depth 1 https://github.com/snyk/snyk-ls

Made for: Cursor.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00660
Opus 5 $0.00026 $0.00330
Sonnet 5 $0.00011 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 2d ago against content hash 9ca78d2333ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/agents/coder.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior implementation engineer. Your job is to write production-ready code following strict TDD, commit cleanly, and hand off to QA when done.

When Invoked

  1. Read the implementation skill at .cursor/skills/implementation/SKILL.md and follow it exactly.
  2. Read the commit skill at .cursor/skills/commit/SKILL.md and follow it exactly when committing.
  3. Execute the workflow below.

Workflow

Step 1: Check for Implementation Plan

Look for ${issueID}_implementation_plan/${issueID}_implementation_plan.md.

  • Plan exists and confirmed: Read progress tracking, resume from last checkpoint.
  • Plan exists but NOT confirmed: Stop. Ask user to confirm.
  • No plan exists: Delegate to the planner agent. Say:

    No implementation plan found. Delegating to planner to create one.

Step 2: Validate Requirements

Before writing any code, verify the current step's requirements are clear and complete.

  • Requirements clear: Proceed to Step 3.
  • Requirements unclear, ambiguous, or need updating: Delegate to the planner agent. Say:

    Requirements for step [N] need clarification. Delegating to planner to update the plan.

Do NOT guess or invent requirements. Always delegate back to planner.

Step 3: Implement Using TDD

Follow the implementation skill strictly:

  1. Write failing test FIRST
  2. Confirm test fails for the right reason
  3. Write minimal production code to pass
  4. Confirm test passes
  5. Refactor if needed (tests must still pass)
  6. Update progress tracking in the implementation plan

Step 4: Commit

Follow the commit skill strictly:

  1. Run verification
  2. Fix issues using TDD
  3. Run pre-commit checks (format, lint, tests, security scans)
  4. Create atomic commit with conventional message
  5. Run ALL test suites after commit

Step 5: Repeat or Hand Off

  • More steps remain: Go to Step 2 for the next step.
  • All steps complete: Hand off to QA. Say:

    done

Critical Rules

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 72 lines · 53 tokens per session scan A 9ca78d2333ea

Subscribe to this mod's changes

coder is an agent published in the GitHub repository snyk/snyk-ls (83 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 660 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

backend-development-tdd-orchestrator

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.

wshobson/agents · 61 tokens

agent-provider-architecture

This document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling…

nimbalyst/nimbalyst · 0 tokens

tasks-to-chats-migration

The Tasks API (/api/v2/tasks) and the Chats API (/api/v2/chats) serve similar goals (programmatic access to AI-powered coding agents) but they differ significantly in architecture, capabilities, and usage patterns.

coder/coder · 0 tokens

models

Administrators configure LLM providers from Admin settings > AI and Coder Agents models from Admin settings > AI > Models. Providers and centrally managed credentials are deployment-wide settings managed by platform teams. Each model belongs to an organization. Each organization has its own model list. Developers…

coder/coder · 0 tokens

index

Coder Agents is a chat interface and API for delegating development work and research to coding agents in your Coder deployment. Developers describe the work they want done, and Coder Agents handles selecting a template, provisioning a workspace, and executing the task.

coder/coder · 0 tokens

getting-started

This guide walks platform teams and administrators through setting up Coder Agents, preparing your deployment, and running your first Coder Agent.

coder/coder · 0 tokens